Reasoning with Transformer-based Models: Deep Learning, but Shallow ReasoningDownload PDF

Jun 22, 2021 (edited Sep 14, 2021)AKBC 2021Readers: Everyone
  • Keywords: Logical Reasoning, Mathematical Reasoning, Commonsense Reasoning, Transformers, BERT
  • Abstract: Recent years have seen impressive performance of transformer-based models on different natural language processing tasks. However, it is not clear to what degree the transformers can reason on natural language. To shed light on this question, this survey paper discusses the performance of transformers on different reasoning tasks, including mathematical reasoning, commonsense reasoning, and logical reasoning. We point out successes and limitations, of both empirical and theoretical nature.
  • Subject Areas: Question Answering and Reasoning
  • Archival Status: Archival
  • Supplementary Material: zip
10 Replies